© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33097
    Prev
    Next
    INDEX
    Explanations

    you plus action or state

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on direct personal address, especially the second‐person pronoun “you.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     since
    -1.36
     that
    -1.29
     when
    -1.20
     had
    -1.20
     recently
    -1.06
     界
    -1.04
     already
    -1.04
     lately
    -1.02
     but
    -1.00
     just
    -1.00
    POSITIVE LOGITS
     into
    1.34
    weren
    1.29
    wasn
    1.21
    ('/:
    1.02
     위한
    1.01
    xiii
    1.00
    ுக்கு
    0.99
    ŕ
    0.96
    地看着
    0.96
     totalSupply
    0.96
    Activations Density 0.032%

    No Known Activations